Prompt Engineering
+5 XP
Category
Prompt Leaking
18 articles
Prompt Engineering
+5 XP
Prompt Injection Attacks — From Prompt Engineering to Exploitation | Part 4
Prompt injection attacks explained — direct injection, indirect injection, jailbreaking and defence bypass, with real examples. Day 4 of the…
AI Basics
+5 XP
How Hackers Attack AI Systems — 6 Real Attack Types Explained Simply (2026) | AI Basics Day 4
How hackers attack AI systems — prompt injection, adversarial examples, jailbreaking and more, explained in plain language. Day 4 of…
Hacking AI
+5 XP
ChatGPT Security Vulnerabilities — What Ethical Hackers Found in 2026
The real ChatGPT security vulnerabilities found by ethical hackers in 2026. I break down conversation theft, memory exploitation, GPT supply…
LLM Hacking
+5 XP
LLM Hacking Tutorial — How Security Researchers Break Language Models (2026)
Complete LLM hacking tutorial for 2026. I walk through 6 stages from recon to automated scanning — with real payloads,…
AI LLM Hacking Course
+5 XP
How to Extract a System Prompt Using Advanced Techniques in 2026 | Day 18
Master How to extract a system system prompt using Advanced Techniques in 2026. 15 ranked techniques, model resistance profiling, Burp…
AI LLM Hacking Course
+5 XP
LLM07 System Prompt Leakage — 15 Extraction Techniques Every AI Red Teamer Needs | Day 11
Master LLM07 System Prompt Leakage in 2026. 15 extraction techniques — direct requests, translation tricks, roleplay framing, token completion and…
AI in Hacking
+5 XP
PROMPTFLUX and PROMPTSTEAL explained — AI Malware That Queries LLMs Mid-Attack
PROMPTFLUX and PROMPTSTEAL explained — the AI malware families that query LLMs mid-execution to evade detection, documented in M-Trends 2026,…
AI LLM Hacking Course
+5 XP
LLM02 Sensitive Information Disclosure — How LLMs Leak PII, Credentials & System Data | AI LLM Hacking Course Day 6
Master LLM02 Sensitive Information Disclosure in 2026. API keys in system prompts, PII from training data, credential extraction and system…
AI in Hacking
+5 XP
AI Code Assistant Backdoor Injection 2026 — When Copilot Writes Malicious Code
How attackers inject backdoors into AI coding assistants via training data poisoning in 2026. GitHub Copilot, supply chain risks, and…